We developed a novel method to detect the presence of unburned diesel fuel in lubricating oil for internal combustion engine. The method is based on the use of an array of different gas microsensors based on metal oxide thin films. The sensor array, exposed to the volatiles of different engine oil samples contaminated in different percentages by diesel, resulted to be appreciable sensitive to them. Principal Component Analysis (PCA) applied to the sensor response data-set gave a first proof of the sensor array ability to discriminate among the different contaminated oils. Moreover, in order to get information about the headspace composition of the fuel-contaminated engine oils samples, we analyzed the engine oil samples by Static Headspace Solid Phase Micro Extraction/Gas Chromatograph/Mass Spectrometer (SHS-SPME/GC/MS).